University of Hertfordshire

Evolving Spiking Neural Networks to Control Animats for Temporal Pattern Recognition and Foraging

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Standard

Evolving Spiking Neural Networks to Control Animats for Temporal Pattern Recognition and Foraging. / Bensmail, Chama; Steuber, Volker; Davey, Neil; Wrobel, Borys.

2017 IEEE Symposium Series on Computational Intelligence, SSCI 2017 - Proceedings. Vol. 2018-January IEEE, 2018. p. 1-8.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Harvard

Bensmail, C, Steuber, V, Davey, N & Wrobel, B 2018, Evolving Spiking Neural Networks to Control Animats for Temporal Pattern Recognition and Foraging. in 2017 IEEE Symposium Series on Computational Intelligence, SSCI 2017 - Proceedings. vol. 2018-January, IEEE, pp. 1-8. https://doi.org/10.1109/SSCI.2017.8285411

APA

Bensmail, C., Steuber, V., Davey, N., & Wrobel, B. (2018). Evolving Spiking Neural Networks to Control Animats for Temporal Pattern Recognition and Foraging. In 2017 IEEE Symposium Series on Computational Intelligence, SSCI 2017 - Proceedings (Vol. 2018-January, pp. 1-8). IEEE. https://doi.org/10.1109/SSCI.2017.8285411

Vancouver

Bensmail C, Steuber V, Davey N, Wrobel B. Evolving Spiking Neural Networks to Control Animats for Temporal Pattern Recognition and Foraging. In 2017 IEEE Symposium Series on Computational Intelligence, SSCI 2017 - Proceedings. Vol. 2018-January. IEEE. 2018. p. 1-8 https://doi.org/10.1109/SSCI.2017.8285411

Author

Bensmail, Chama ; Steuber, Volker ; Davey, Neil ; Wrobel, Borys. / Evolving Spiking Neural Networks to Control Animats for Temporal Pattern Recognition and Foraging. 2017 IEEE Symposium Series on Computational Intelligence, SSCI 2017 - Proceedings. Vol. 2018-January IEEE, 2018. pp. 1-8

Bibtex

@inproceedings{3fabe324d8c54cd7a75b4a1730f99dde,
title = "Evolving Spiking Neural Networks to Control Animats for Temporal Pattern Recognition and Foraging",
abstract = "We evolved spiking neural networks (SNNs) to control animats in a task requiring temporal pattern recognition and foraging in a 2D environment with two types of objects emitting patterns: a target and a distractor. The target emits a specific temporal pattern composed of two components, while the distractor emits random patterns that are all the other combinations of these two components. The fitness function rewarded finding targets and avoiding distractors. We show that the evolved animats are robust to changes of the number of objects in the environment, strength of the actuators, duration of signals, intervals between signals in the pattern and between patterns. Our long term goal is to understand the mechanisms governing the neural networks that accomplish simple but not trivial computational tasks inspired by minimally cognitive abilities of animals, such as phonotaxis.",
keywords = "adaptive exponential (AdEX) integrate-and-fire neuron, animat control, artificial evolution, complex networks, evolutionary algorithm, spiking neural networks, temporal pattern recognition",
author = "Chama Bensmail and Volker Steuber and Neil Davey and Borys Wrobel",
year = "2018",
month = "2",
day = "8",
doi = "10.1109/SSCI.2017.8285411",
language = "English",
isbn = "978-1-5386-2727-3",
volume = "2018-January",
pages = "1--8",
booktitle = "2017 IEEE Symposium Series on Computational Intelligence, SSCI 2017 - Proceedings",
publisher = "IEEE",

}

RIS

TY - GEN

T1 - Evolving Spiking Neural Networks to Control Animats for Temporal Pattern Recognition and Foraging

AU - Bensmail, Chama

AU - Steuber, Volker

AU - Davey, Neil

AU - Wrobel, Borys

PY - 2018/2/8

Y1 - 2018/2/8

N2 - We evolved spiking neural networks (SNNs) to control animats in a task requiring temporal pattern recognition and foraging in a 2D environment with two types of objects emitting patterns: a target and a distractor. The target emits a specific temporal pattern composed of two components, while the distractor emits random patterns that are all the other combinations of these two components. The fitness function rewarded finding targets and avoiding distractors. We show that the evolved animats are robust to changes of the number of objects in the environment, strength of the actuators, duration of signals, intervals between signals in the pattern and between patterns. Our long term goal is to understand the mechanisms governing the neural networks that accomplish simple but not trivial computational tasks inspired by minimally cognitive abilities of animals, such as phonotaxis.

AB - We evolved spiking neural networks (SNNs) to control animats in a task requiring temporal pattern recognition and foraging in a 2D environment with two types of objects emitting patterns: a target and a distractor. The target emits a specific temporal pattern composed of two components, while the distractor emits random patterns that are all the other combinations of these two components. The fitness function rewarded finding targets and avoiding distractors. We show that the evolved animats are robust to changes of the number of objects in the environment, strength of the actuators, duration of signals, intervals between signals in the pattern and between patterns. Our long term goal is to understand the mechanisms governing the neural networks that accomplish simple but not trivial computational tasks inspired by minimally cognitive abilities of animals, such as phonotaxis.

KW - adaptive exponential (AdEX) integrate-and-fire neuron

KW - animat control

KW - artificial evolution

KW - complex networks

KW - evolutionary algorithm

KW - spiking neural networks

KW - temporal pattern recognition

UR - http://www.scopus.com/inward/record.url?scp=85046122496&partnerID=8YFLogxK

U2 - 10.1109/SSCI.2017.8285411

DO - 10.1109/SSCI.2017.8285411

M3 - Conference contribution

SN - 978-1-5386-2727-3

VL - 2018-January

SP - 1

EP - 8

BT - 2017 IEEE Symposium Series on Computational Intelligence, SSCI 2017 - Proceedings

PB - IEEE

ER -